ESMFold
A protein structure prediction model developed by Meta AI Research, based on the protein language model ESM-2. It predicts three-dimensional protein structures rapidly without requiring multiple sequence alignment, with inference speed substantially faster than AlphaFold2.
Timeline (last 90 days)
Designability is a commonly used evaluation criterion in generative protein design: the generated backbone is fed into an independent sequence design model (such as ProteinMPNN), and the predicted sequence is then refolded using a structure prediction tool (such as ESMFold or AlphaFold); if the predicted structure is highly consistent with the original backbone (usually judged by an scRMSD threshold), the backbone is considered designable.
ESMFold and EvoDiff released by Meta support protein sequence generation.
As models such as AlphaFold and ESMFold have gradually matured, an increasing number of research projects have begun running structure predictions at the proteome scale.
All Facts (3)
Designability is a commonly used evaluation criterion in generative protein design: the generated backbone is fed into an independent sequence design model (such as ProteinMPNN), and the predicted sequence is then refolded using a structure prediction tool (such as ESMFold or AlphaFold); if the predicted structure is highly consistent with the original backbone (usually judged by an scRMSD threshold), the backbone is considered designable.
50%UnverifiedESMFold and EvoDiff released by Meta support protein sequence generation.
50%UnverifiedAs models such as AlphaFold and ESMFold have gradually matured, an increasing number of research projects have begun running structure predictions at the proteome scale.
50%